由于物体的异质尺度，肾脏病理图像的全面语义分割具有挑战性。例如，在整个幻灯片图像（WSI）上，肾小球的横截面区域的距离可能比周围毛细管的64倍，这使得以相同尺度上的同一贴片对两个对象进行分割是不切实际的。为了解决这个缩放问题，先前的研究通常已经训练了多个分割网络，以匹配异质组织类型的最佳像素分辨率。这种多网络解决方案是资源密集型的，无法对组织类型之间的空间关系进行建模。在本文中，我们提出了Omni-Seg+网络，这是一种通过单个神经网络实现多对象（六种组织类型）和多尺度（5倍至40倍尺度）的多尺度（5倍至40倍尺度）的动态神经网络。本文的贡献是三个方面的：（1）提出了一种新型的量表感知控制器，以将动态神经网络从单尺度到多尺度推广； （2）引入了伪标签的半监督一致性正规化，以建模未经注释的组织类型的尺度相关性成单个端到端的学习范式； （3）直接将在人类肾脏图像训练的模型中直接应用于小鼠肾脏图像，而无需再培训，就可以证明高尺度感知的概括。通过从三种不同分辨率下从六种组织类型中学习的约150,000个人类病理图像斑块，我们的方法根据人类的视觉评估和图像词的评估（即空间转录组学）获得了卓越的分割性能。官方实施可在https://github.com/ddrrnn123/omni-seg上获得。

最先进的蒸馏方法主要基于中间层的深层特征，而logit蒸馏的重要性被极大地忽略了。为了提供研究逻辑蒸馏的新观点，我们将经典的KD损失重新分为两个部分，即目标类知识蒸馏（TCKD）和非目标类知识蒸馏（NCKD）。我们凭经验研究并证明了这两个部分的影响：TCKD转移有关训练样本“难度”的知识，而NCKD是Logit蒸馏起作用的重要原因。更重要的是，我们揭示了经典的KD损失是一种耦合的配方，该配方抑制了NCKD的有效性，并且（2）限制了平衡这两个部分的灵活性。为了解决这些问题，我们提出了脱钩的知识蒸馏（DKD），使TCKD和NCKD能够更有效，更灵活地发挥其角色。与基于功能的复杂方法相比，我们的DKD可相当甚至更好的结果，并且在CIFAR-100，ImageNet和MS-Coco数据集上具有更好的培训效率，用于图像分类和对象检测任务。本文证明了Logit蒸馏的巨大潜力，我们希望它对未来的研究有所帮助。该代码可从https://github.com/megvii-research/mdistiller获得。

整合跨部门多模式数据（例如，放射学，病理学，基因组和临床数据）无处不在，在脑癌诊断和存活预测中无处不在。迄今为止，这种整合通常是由人类医师（以及专家小组）进行的，可以是主观的和半定量的。然而，多模式深度学习的最新进展已为利用这种过程以更加客观和定量的方式打开了一扇门。不幸的是，先前在脑癌生存预测上使用四种模式的艺术受到“完整模式”设置的限制（即，所有可用方式）。因此，关于如何有效预测脑癌生存的问题仍然存在开放性问题，从放射学，病理学，基因组和人口统计学数据中（例如，可能无法为患者收集一种或多种方式）。例如，我们是否应该同时使用完整和不完整的数据，更重要的是，如何使用这些数据？为了回答前面的问题，我们将跨部门多模式数据的多模式学习推广到缺失的数据设置。我们的贡献是三个方面：1）我们引入了最佳的多模式学习，其中缺少数据（MMD）管道具有优化的硬件消耗和计算效率； 2）我们将有关放射学，病理，基因组和人口统计学数据的多模式学习扩展到缺失的数据情景； 3）收集了一个大规模的公共数据集（有962名患者），以系统地评估胶质瘤肿瘤存活预测。所提出的方法将生存预测的C索引从0.7624提高到0.8053。

这项工作同时考虑了典型的监督学习任务中深度表示的可区分性和可传递性属性，即图像分类。通过全面的时间分析，我们观察到这两个属性之间的权衡。随着培训的进展，可区分性不断提高，而转移性在后来的培训期间大大降低。从信息 - 底层理论的角度来看，我们揭示了可区分性和可传递性之间的不相容性归因于输入信息的过度压缩。更重要的是，我们研究了为什么和为什么如何减轻过度压缩的信息，并进一步提出一个学习框架，称为对比度的时间编码〜（CTC），以抵消过度压缩并减轻不相容性。广泛的实验验证了CTC成功缓解了不相容性，从而产生了歧视性和可转移表示形式。在图像分类任务和挑战转移学习任务上实现了明显的改进。我们希望这项工作将提高传统监督学习环境中可转移性属性的重要性。代码可从https://github.com/dtennant/dt-tradeoff获得。

关于Giga-Pixel病理学图像的计算机辅助定量分析提供了精密药物的新大道。该创新主要集中在癌症病理学（即，肿瘤分割和表征）上。在非癌症病理学中，可以要求学习算法同时检查更全面的组织类型，作为多标签设置。现有技术通常需要训练多个分段网络，以匹配非均相组织类型的域特异性知识（例如，肾小球簇，肾小球单元，近端管，远端管，梗塞和动脉）。在本文中，我们提出了一种动态单分割网络（OMNI-SEG），该网络（OMNI-SEG）学习使用部分标记的图像（即，仅针对每个训练图像标记一个组织类型）进行多种组织类型进行肾脏病理学。通过从六种组织类型学习〜150,000的Patch-Wise病理图像，与先前的多网络和多头设计相比，所提出的Omni-SEG网络实现了卓越的分割精度和更少的资源消耗。在测试阶段，所提出的方法仅使用“部分标记”训练图像获得“完全标记的”组织分割结果。源代码可在https://github.com/ddrrnn123/omni-seg中获得。

开创性双编码器预训练工作（例如，剪辑并对齐）揭示了与对比学习对齐多模态表示的潜力。然而，这些作品需要大量的数据和计算资源（例如，十亿级Web数据和数百个GPU），这阻止了从再生产和进一步探索的资源有限的研究人员。为此，我们探讨了一堆简单但有效的启发式，并提供了全面的培训指导，使我们能够与有限的资源进行双编码器多模态表示对齐。我们为竞争结果提供可重复的强大基线，即Zerovl，只有1400万公共访问的学术数据集和8 v100 GPU。此外，我们收集100米Web数据进行预培训，而不是最先进的方法实现可比或优越的结果，进一步证明了我们对大规模数据的方法的有效性。我们希望这项工作将为多模态预培训的未来研究提供有用的数据点和经验。我们的代码和预先训练的型号将被释放，以促进研究界。

Our work focuses on tackling the challenging but natural visual recognition task of long-tailed data distribution (i.e., a few classes occupy most of the data, while most classes have rarely few samples). In the literature, class re-balancing strategies (e.g., re-weighting and re-sampling) are the prominent and effective methods proposed to alleviate the extreme imbalance for dealing with long-tailed problems. In this paper, we firstly discover that these rebalancing methods achieving satisfactory recognition accuracy owe to that they could significantly promote the classifier learning of deep networks. However, at the same time, they will unexpectedly damage the representative ability of the learned deep features to some extent. Therefore, we propose a unified Bilateral-Branch Network (BBN) to take care of both representation learning and classifier learning simultaneously, where each branch does perform its own duty separately. In particular, our BBN model is further equipped with a novel cumulative learning strategy, which is designed to first learn the universal patterns and then pay attention to the tail data gradually. Extensive experiments on four benchmark datasets, including the large-scale iNaturalist ones, justify that the proposed BBN can significantly outperform state-of-the-art methods. Furthermore, validation experiments can demonstrate both our preliminary discovery and effectiveness of tailored designs in BBN for long-tailed problems. Our method won the first place in the iNaturalist 2019 large scale species classification competition, and our code is open-source and available at https://github.com/Megvii-Nanjing/BBN . * Q. Cui and Z.-M. Chen's contribution was made when they were interns in Megvii Research Nanjing, Megvii Technology, China. X.

A recent study has shown a phenomenon called neural collapse in that the within-class means of features and the classifier weight vectors converge to the vertices of a simplex equiangular tight frame at the terminal phase of training for classification. In this paper, we explore the corresponding structures of the last-layer feature centers and classifiers in semantic segmentation. Based on our empirical and theoretical analysis, we point out that semantic segmentation naturally brings contextual correlation and imbalanced distribution among classes, which breaks the equiangular and maximally separated structure of neural collapse for both feature centers and classifiers. However, such a symmetric structure is beneficial to discrimination for the minor classes. To preserve these advantages, we introduce a regularizer on feature centers to encourage the network to learn features closer to the appealing structure in imbalanced semantic segmentation. Experimental results show that our method can bring significant improvements on both 2D and 3D semantic segmentation benchmarks. Moreover, our method ranks 1st and sets a new record (+6.8% mIoU) on the ScanNet200 test leaderboard. Code will be available at https://github.com/dvlab-research/Imbalanced-Learning.

When using LiDAR semantic segmentation models for safety-critical applications such as autonomous driving, it is essential to understand and improve their robustness with respect to a large range of LiDAR corruptions. In this paper, we aim to comprehensively analyze the robustness of LiDAR semantic segmentation models under various corruptions. To rigorously evaluate the robustness and generalizability of current approaches, we propose a new benchmark called SemanticKITTI-C, which features 16 out-of-domain LiDAR corruptions in three groups, namely adverse weather, measurement noise and cross-device discrepancy. Then, we systematically investigate 11 LiDAR semantic segmentation models, especially spanning different input representations (e.g., point clouds, voxels, projected images, and etc.), network architectures and training schemes. Through this study, we obtain two insights: 1) We find out that the input representation plays a crucial role in robustness. Specifically, under specific corruptions, different representations perform variously. 2) Although state-of-the-art methods on LiDAR semantic segmentation achieve promising results on clean data, they are less robust when dealing with noisy data. Finally, based on the above observations, we design a robust LiDAR segmentation model (RLSeg) which greatly boosts the robustness with simple but effective modifications. It is promising that our benchmark, comprehensive analysis, and observations can boost future research in robust LiDAR semantic segmentation for safety-critical applications.

Hybrid unmanned aerial vehicles (UAVs) integrate the efficient forward flight of fixed-wing and vertical takeoff and landing (VTOL) capabilities of multicopter UAVs. This paper presents the modeling, control and simulation of a new type of hybrid micro-small UAVs, coined as lifting-wing quadcopters. The airframe orientation of the lifting wing needs to tilt a specific angle often within $ 45$ degrees, neither nearly $ 90$ nor approximately $ 0$ degrees. Compared with some convertiplane and tail-sitter UAVs, the lifting-wing quadcopter has a highly reliable structure, robust wind resistance, low cruise speed and reliable transition flight, making it potential to work fully-autonomous outdoor or some confined airspace indoor. In the modeling part, forces and moments generated by both lifting wing and rotors are considered. Based on the established model, a unified controller for the full flight phase is designed. The controller has the capability of uniformly treating the hovering and forward flight, and enables a continuous transition between two modes, depending on the velocity command. What is more, by taking rotor thrust and aerodynamic force under consideration simultaneously, a control allocation based on optimization is utilized to realize cooperative control for energy saving. Finally, comprehensive Hardware-In-the-Loop (HIL) simulations are performed to verify the advantages of the designed aircraft and the proposed controller.